A3S: A General Active Clustering Method with Pairwise Constraints

Xun Deng, Junlong Liu, Han Zhong, Fuli Feng, Chen Shen, Xiangnan He, Jieping Ye, Zheng Wang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:10488-10505, 2024.

Abstract

Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying. Conventional approaches with semi-supervised clustering schemes encounter high query costs when applied to large datasets with numerous classes. To address these limitations, we propose a novel Adaptive Active Aggregation and Splitting (A3S) framework, falling within the cluster-adjustment scheme in active clustering. A3S features strategic active clustering adjustment on the initial cluster result, which is obtained by an adaptive clustering algorithm. In particular, our cluster adjustment is inspired by the quantitative analysis of Normalized mutual information gain under the information theory framework and can provably improve the clustering quality. The proposed A3S framework significantly elevates the performance and scalability of active clustering. In extensive experiments across diverse real-world datasets, A3S achieves desired results with significantly fewer human queries compared with existing methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-deng24b, title = {{A}3{S}: A General Active Clustering Method with Pairwise Constraints}, author = {Deng, Xun and Liu, Junlong and Zhong, Han and Feng, Fuli and Shen, Chen and He, Xiangnan and Ye, Jieping and Wang, Zheng}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {10488--10505}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/deng24b/deng24b.pdf}, url = {https://proceedings.mlr.press/v235/deng24b.html}, abstract = {Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying. Conventional approaches with semi-supervised clustering schemes encounter high query costs when applied to large datasets with numerous classes. To address these limitations, we propose a novel Adaptive Active Aggregation and Splitting (A3S) framework, falling within the cluster-adjustment scheme in active clustering. A3S features strategic active clustering adjustment on the initial cluster result, which is obtained by an adaptive clustering algorithm. In particular, our cluster adjustment is inspired by the quantitative analysis of Normalized mutual information gain under the information theory framework and can provably improve the clustering quality. The proposed A3S framework significantly elevates the performance and scalability of active clustering. In extensive experiments across diverse real-world datasets, A3S achieves desired results with significantly fewer human queries compared with existing methods.} }
Endnote
%0 Conference Paper %T A3S: A General Active Clustering Method with Pairwise Constraints %A Xun Deng %A Junlong Liu %A Han Zhong %A Fuli Feng %A Chen Shen %A Xiangnan He %A Jieping Ye %A Zheng Wang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-deng24b %I PMLR %P 10488--10505 %U https://proceedings.mlr.press/v235/deng24b.html %V 235 %X Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying. Conventional approaches with semi-supervised clustering schemes encounter high query costs when applied to large datasets with numerous classes. To address these limitations, we propose a novel Adaptive Active Aggregation and Splitting (A3S) framework, falling within the cluster-adjustment scheme in active clustering. A3S features strategic active clustering adjustment on the initial cluster result, which is obtained by an adaptive clustering algorithm. In particular, our cluster adjustment is inspired by the quantitative analysis of Normalized mutual information gain under the information theory framework and can provably improve the clustering quality. The proposed A3S framework significantly elevates the performance and scalability of active clustering. In extensive experiments across diverse real-world datasets, A3S achieves desired results with significantly fewer human queries compared with existing methods.
APA
Deng, X., Liu, J., Zhong, H., Feng, F., Shen, C., He, X., Ye, J. & Wang, Z.. (2024). A3S: A General Active Clustering Method with Pairwise Constraints. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:10488-10505 Available from https://proceedings.mlr.press/v235/deng24b.html.

Related Material